© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128559
    Prev
    Next
    INDEX
    Explanations

    javascript api and databases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
                
    -1.14
    LLYWOOD
    -1.09
    おい
    -0.98
    ут
    -0.98
     colgantes
    -0.98
     elders
    -0.97
     fahr
    -0.97
     MethodInfo
    -0.97
                    
    -0.96
    ,”
    -0.96
    POSITIVE LOGITS
     what
    1.58
     nedenle
    1.28
    思います
    1.21
     preocupaciones
    1.16
     Schauspielerin
    1.16
    jeto
    1.16
    biť
    1.15
     試
    1.14
    などと
    1.14
    Beskrivning
    1.13
    Activations Density 0.111%

    No Known Activations